AI Paper Atlas

Research map / Continual learning / Continual fine-tuning of LLMs

Meta-UCF: Unified Task-Conditioned LoRA Generation for Continual Learning in Large Language Models

ShiLin Xiao, Tianxiang Xu, Canran Xiao, Weihao Luo, Liwei Hou, Chuangxin Zhao

ICLR 2026 · Continual learning › Continual fine-tuning of LLMs · approach: Low-rank and model-merging adaptation

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add orthogonality penalty Lorth (ablation)Meta-UCF · Std-CL 5average accuracy: 83.9 -> 85.6Improved
add orthogonality penalty Lorth (ablation)Meta-UCF · Long-CL 15average accuracy: 68.5 -> 70.7Improved
add meta-contrastive loss Lctr (ablation)Meta-UCF · Std-CL 5average accuracy: 84.1 -> 85.6Improved
add meta-contrastive loss Lctr (ablation)Meta-UCF · Long-CL 15forgetting ratio: 12.7 -> 11.5Improved
add bias calibration (ablation)Meta-UCF · Long-CL 15average accuracy: 69.4 -> 70.7Improved
use layer-normalised mean pooling instead of last CLS (ablation)Meta-UCF · Std-CL 5average accuracy: 82.1 -> 85.6Improved
add task-conditioned generator instead of static LoRA (ablation)Meta-UCF · Long-CL 15average accuracy: 64.9 -> 70.7Improved
use historical replay support instead of current-task-only support (ablation)Meta-UCF · Std-CL 5average accuracy: 83.4 -> 85.6Improved
increase replay buffer from 256 to 512 (ablation)Meta-UCF · Long-CL 15forgetting ratio: 11.5 -> 10.9Improved
reduce LoRA rank from 8 to 4 (ablation)Meta-UCF · Long-CL 15average accuracy: 70.7 -> 69.0Hurt
increase LoRA rank from 8 to 16 (ablation)Meta-UCF · Long-CL 15average accuracyNo clear effect
restrict LoRA to upper half of layers (ablation)Meta-UCF · Std-CL 5average accuracy: 85.6 -> 84.9Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy